{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UWGUOYEX7CZ6ENQYL6LV5JNDAQ","short_pith_number":"pith:UWGUOYEX","schema_version":"1.0","canonical_sha256":"a58d476097f8b3e236185f975ea5a3040492eb48fab92b24125a8ac157fd6946","source":{"kind":"arxiv","id":"2606.01620","version":1},"attestation_state":"computed","paper":{"title":"Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Jiaolong Yang, Shoukang Hu, Sicheng Xu, Yichuan Wang, Yizhong Zhang, Yu Deng, Zhan Chen","submitted_at":"2026-06-01T03:12:23Z","abstract_excerpt":"Video diffusion models have significantly advanced portrait video generation, yet their high computational demands limit their use in interactive applications. This work presents a framework for streamable talking portrait video generation conditioned on speech audio and reference images. Designed meticulously for streaming scenarios, it features a causal video VAE for deep latent compression and an autoregressive latent denoising model. Our causal VAE integrates a variable number of reference images as guidance, allowing the network to focus on dynamic information rather than static appearanc"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.01620","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T03:12:23Z","cross_cats_sorted":[],"title_canon_sha256":"981454e19d9729af6d3ec4fccbaf56c56832d3940ad93fd542ad333f15119001","abstract_canon_sha256":"b041efaac856257a4dce63fa6531914685cc9fa08e6f3af6e3020c56d037a079"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:38.259538Z","signature_b64":"Gq4ngvWAxXPef57MDBFAIS4nsl4kq3N+re+ssrqt4iI1H586Om3LklMyeeQVRz/CYX5EVyj+UfSajd6DQqxxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a58d476097f8b3e236185f975ea5a3040492eb48fab92b24125a8ac157fd6946","last_reissued_at":"2026-06-02T02:04:38.259128Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:38.259128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Jiaolong Yang, Shoukang Hu, Sicheng Xu, Yichuan Wang, Yizhong Zhang, Yu Deng, Zhan Chen","submitted_at":"2026-06-01T03:12:23Z","abstract_excerpt":"Video diffusion models have significantly advanced portrait video generation, yet their high computational demands limit their use in interactive applications. This work presents a framework for streamable talking portrait video generation conditioned on speech audio and reference images. Designed meticulously for streaming scenarios, it features a causal video VAE for deep latent compression and an autoregressive latent denoising model. Our causal VAE integrates a variable number of reference images as guidance, allowing the network to focus on dynamic information rather than static appearanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01620","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.01620/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.01620","created_at":"2026-06-02T02:04:38.259185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01620v1","created_at":"2026-06-02T02:04:38.259185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01620","created_at":"2026-06-02T02:04:38.259185+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWGUOYEX7CZ6","created_at":"2026-06-02T02:04:38.259185+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWGUOYEX7CZ6ENQY","created_at":"2026-06-02T02:04:38.259185+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWGUOYEX","created_at":"2026-06-02T02:04:38.259185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UWGUOYEX7CZ6ENQYL6LV5JNDAQ","json":"https://pith.science/pith/UWGUOYEX7CZ6ENQYL6LV5JNDAQ.json","graph_json":"https://pith.science/api/pith-number/UWGUOYEX7CZ6ENQYL6LV5JNDAQ/graph.json","events_json":"https://pith.science/api/pith-number/UWGUOYEX7CZ6ENQYL6LV5JNDAQ/events.json","paper":"https://pith.science/paper/UWGUOYEX"},"agent_actions":{"view_html":"https://pith.science/pith/UWGUOYEX7CZ6ENQYL6LV5JNDAQ","download_json":"https://pith.science/pith/UWGUOYEX7CZ6ENQYL6LV5JNDAQ.json","view_paper":"https://pith.science/paper/UWGUOYEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01620&json=true","fetch_graph":"https://pith.science/api/pith-number/UWGUOYEX7CZ6ENQYL6LV5JNDAQ/graph.json","fetch_events":"https://pith.science/api/pith-number/UWGUOYEX7CZ6ENQYL6LV5JNDAQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWGUOYEX7CZ6ENQYL6LV5JNDAQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWGUOYEX7CZ6ENQYL6LV5JNDAQ/action/storage_attestation","attest_author":"https://pith.science/pith/UWGUOYEX7CZ6ENQYL6LV5JNDAQ/action/author_attestation","sign_citation":"https://pith.science/pith/UWGUOYEX7CZ6ENQYL6LV5JNDAQ/action/citation_signature","submit_replication":"https://pith.science/pith/UWGUOYEX7CZ6ENQYL6LV5JNDAQ/action/replication_record"}},"created_at":"2026-06-02T02:04:38.259185+00:00","updated_at":"2026-06-02T02:04:38.259185+00:00"}